Dominik Schiller

convolutional neural network (2) prototype learning (1) prosody analysis (1) speaker embedding (1) speaker verification (1) audio classification (1) ensemble classification (1) recurrent neural network (1) deep neural network (1) feature engineering (1) latent space exploration (1) explainable artificial intelligence (1) speech generation (1) voice generation (1) paralinguistic recognition (1) bioacoustic classification (1) whale sound detection (1) feature masking (1) decision fusion (1) voice quality (1)